Method and device for intelligent control of heating furnace combustion based on a big data cloud platform

Abstract

The present disclosure provides a method and device for intelligent control of heating furnace combustion based on a big data cloud platform, which relates to the technical field of artificial intelligence control. The method includes: construction of big data cloud platform based on production and operation parameters of the heating furnace; identification of key factors in the production process of the heating furnace by using big data mining technology; independent deployment of traditional heating furnace combustion control systems based on the mechanism model; and integration of cloud platform big data expert knowledge base and the heating furnace combustion intelligent control system.

What is claimed is: 
     
         1 . A method for intelligent control of heating furnace combustion based on a big data cloud platform, comprising:
 S 1 : building the big data cloud platform based on production and operation parameters of a heating furnace;   S 2 : identifying and analyzing key factors in a production process of the heating furnace, by using big data mining technology, based on the big data cloud platform, to obtain a relevant data knowledge base and a big data decision-making knowledge base;   wherein step S 2  of identifying and analyzing the key factors in the production process of the heating furnace, by using the big data mining technology, based on the big data cloud platform, to obtain the relevant data knowledge base and the big data decision-making knowledge base comprises:   S 21 : identifying the key factors in the production process of the heating furnace, by using big data mining technology, based on the big data cloud platform, to obtain the relevant data knowledge base;   S 22 : mining an association map of each operating parameter, by intelligent analysis of big data, based on artificial intelligence, machine learning and mode learning methods preset by a parameter data center during operation of the heating furnace, to obtain the big data decision-making knowledge base;   wherein step S 21  of obtaining the relevant data knowledge base comprises:   obtaining a knowledge base of working and furnace conditions, comprising: for different planned mixed assembly, according to different heating sections, and based on steel type, position weight, vacancy layout, target temperature, current temperature, predicted section temperature, weighing a heating system of different slabs, and perceiving furnace and working condition state parameters of the heating furnace for overall planning, to obtain the knowledge base of working and furnace conditions;   obtaining an accuracy evaluation knowledge base for a plate temperature prediction model, comprising: dynamically evaluating prediction accuracy data of a temperature inside a furnace of each grade for adaptive adjustment of an intelligent combustion model, and synthesizing the prediction accuracy data to obtain the accuracy evaluation knowledge base for the plate temperature prediction model;   obtaining a knowledge base for energy efficiency evaluation of the heating furnace, comprising: based on production data, energy data and furnace conditions, forming objective evaluation data of the heating furnace, and synthesizing the objective evaluation data to obtain the knowledge base for energy efficiency evaluation of the heating furnace;   obtaining a knowledge base for furnace pressure discrimination, comprising: according to a standard that a priority of furnace pressure control is higher than that of furnace temperature control, controlling an outlet side of the heating furnace to be in a micro-positive pressure state, and synthesizing control standard data and micro-positive pressure state data, to obtain the knowledge base for furnace pressure discrimination;   obtaining a knowledge base for air-fuel ratio optimization, comprising: setting a reasonable air-fuel ratio, determining a control accuracy of furnace temperature and a control accuracy of atmosphere in each heating section, to obtain the knowledge base for air-fuel ratio optimization;   wherein step S 22  of obtaining the big data decision-making knowledge base comprises:   obtaining a heating target decision-making knowledge base, comprising: describing a heating target specified by each heating furnace through a furnace outlet temperature and a Rolling Delivery Temperature (RDT), to obtain the heating target decision-making knowledge base;   obtaining a heating system decision-making knowledge base, comprising: making statistics on heating curves under various working conditions, and obtaining the heating system decision-making knowledge base;   S 3 : deploying independently a heating furnace combustion control system based on a mechanism model;   S 4 : integrating the heating furnace combustion control system based on the mechanism model with the big data cloud platform, and completing the intelligent control of heating furnace combustion based on the big data cloud platform;   wherein step S 4  of integrating the heating furnace combustion control system based on the mechanism model with the big data cloud platform, and completing the intelligent control of heating furnace combustion based on the big data cloud platform comprises:   integrating the heating furnace combustion control system based on the mechanism model with the big data cloud platform, the big data cloud platform establishing a synchronous data image in the heating furnace according to data collection information, continuously iteratively updating the relevant data knowledge base and the big data decision-making knowledge base, synthesizing information of the relevant data knowledge base and the big data decision-making knowledge base, and sending process and time control parameters to the furnace combustion control system in real time through an Application Programming Interface (API) function, and completing the intelligent control of heating furnace combustion based on the big data cloud platform.   
     
     
         2 . The method according to  claim 1 , wherein step S 1  of building the big data cloud platform based on the production and operation parameters of the heating furnace comprises:
 designing hardware equipment, parameters, and division of labor of the big data cloud platform based on analysis of data storage, access concurrency, heating furnace expert knowledge base, and factors related to calculation demand in a process of model base research and development; 
 wherein the big data cloud platform adopts a three-layer architecture, with a bottom layer being an infrastructure layer, a middle layer being a support layer, and a top layer being a knowledge base service layer. 
 
     
     
         3 . The method according to  claim 2 , wherein the infrastructure layer of the big data cloud platform is configured for hardware resource virtualization and management services, the support layer of the big data cloud platform is configured to provide support for collection, storage, mining, analysis, and visual research and development of parameters during operation of the production process of the heating furnace, the knowledge base service layer is configured to store the key factors of the production process of the heating furnace. 
     
     
         4 . The method according to  claim 1 , wherein step S 3  of deploying independently the heating furnace combustion control system based on the mechanism model comprises:
 S 31 : tracking and correcting material of the heating furnace, corresponding a rolling plan with an actual slab one by one, determining a tracking position, and traversing a slab flow direction, and making tracking correction; 
 S 32 : predicting a temperature rise process of the slab in the heating furnace, and predicting a temperature distribution of the slab at each time section in the heating furnace by using a mathematical model, wherein a slab temperature control equation is shown in formula (1): 
 
       
         
           
             
               
                 
                   
                     
                       
                         ρ 
                         ⁡ 
                         ( 
                         t 
                         ) 
                       
                       ⁢ 
                       
                         Cp 
                         ⁡ 
                         ( 
                         t 
                         ) 
                       
                       ⁢ 
                       
                         
                           ∂ 
                           t 
                         
                         
                           ∂ 
                           τ 
                         
                       
                     
                     = 
                     
                       
                         
                           ∂ 
                           
                             ∂ 
                             x 
                           
                         
                         
                           [ 
                           
                             
                               λ 
                               ⁡ 
                               ( 
                               t 
                               ) 
                             
                             ⁢ 
                             
                               
                                 ∂ 
                                 t 
                               
                               
                                 ∂ 
                                 x 
                               
                             
                           
                           ] 
                         
                       
                       + 
                       
                         
                           ∂ 
                           
                             ∂ 
                             y 
                           
                         
                         
                           [ 
                           
                             
                               λ 
                               ⁡ 
                               ( 
                               t 
                               ) 
                             
                             ⁢ 
                             
                               
                                 ∂ 
                                 t 
                               
                               
                                 ∂ 
                                 y 
                               
                             
                           
                           ] 
                         
                       
                     
                   
                 
                 
                   
                     ( 
                     1 
                     ) 
                   
                 
               
             
           
         
         wherein ρ(t) indicates a density of the slab; Cp(t) indicates a specific heat of the slab; λ(t) indicates a thermal conductivity of the slab; 
         S 33 : establishing a furnace temperature optimization model based on the slab temperature control equation. 
       
     
     
         5 . The method according to  claim 4 , wherein step S 33  of establishing the furnace temperature optimization model based on the slab temperature control equation comprises:
 S 331 : performing offline optimization based on the slab temperature control equation, and establishing a basic furnace temperature table, namely a furnace temperature carpet map; 
 S 332 : performing online dynamic optimization based on the slab temperature control equation, based on a heating process and production rhythm, simulating a temperature rise process of the slab, and calculating a necessary furnace temperature required by a target heating process; 
 S 333 : synthesizing the furnace temperature, giving different weight values to each slab, and obtaining the furnace temperature optimization model based on online optimization of a furnace temperature of each slab, wherein with a position of each slab in a furnace section and a target temperature being different, the weight value within each slab also being different. 
 
     
     
         6 . A device for intelligent control of heating furnace combustion based on a big data cloud platform, wherein the device is applicable to the method according to  claim 1 , and comprises:
 a platform building module, configured to build the big data cloud platform based on production and operation parameters of a heating furnace;   a knowledge base construction module, configured to identify and analyze key factors in a production process of the heating furnace, by using big data mining technology, based on the big data cloud platform, to obtain a relevant data knowledge base and a big data decision-making knowledge base;   a model deployment module, configured to deploy independently a heating furnace combustion control system based on a mechanism model;   an intelligent control module, configured to integrate the heating furnace combustion control system based on the mechanism model with the big data cloud platform, and complete the intelligent control of heating furnace combustion based on the big data cloud platform.